Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eduardo
    -0.08
    .cloud
    -0.07
    (Encoding
    -0.07
     Expansion
    -0.07
    に基づ
    -0.07
    を超え
    -0.07
    来袭
    -0.07
     Cluster
    -0.07
    方向盘
    -0.07
    _BTN
    -0.07
    POSITIVE LOGITS
    iples
    0.07
    esModule
    0.07
     names
    0.07
    命名
    0.07
    inem
    0.07
    余名
    0.07
    حال
    0.07
    xic
    0.07
    ⓞ
    0.07
    .fin
    0.07
    Act Density 0.019%

    No Known Activations